# 
# Written by:
# -- 
# John L. Weatherwax                2009-04-21
# 
# email: wax@alum.mit.edu
# 
# Please send comments and especially bug reports to the
# above email address.
# 
#-----

save_plots = F

#
# EPage 14O
#

DF = read.csv( "../../Data/nicotine.csv", header=TRUE )

lm( Nicotine_content ~ ., data=DF )

# Create the indicator variables specified:
#
DF$IsLorillard = 0
mask = DF$Manufacturer == 'Lorillard'
DF$IsLorillard[mask] = 1

DF$IsMethol = 0
mask = DF$Methol == 'Yes'
DF$IsMethol[mask] = 1

DF$IsFiltered = 0
mask = DF$Filtered == 'filter'
DF$IsFiltered[mask] = 1

m = lm( Nicotine_content ~ IsLorillard + IsMethol + IsFiltered, data=DF )
summary(m)

# Look for interactions among these variables:
#
summary( lm( Nicotine_content ~ IsLorillard + IsMethol + IsFiltered + IsLorillard:IsMethol, data=DF ) )

summary( lm( Nicotine_content ~ IsLorillard + IsMethol + IsFiltered + IsLorillard:IsFiltered, data=DF ) )

summary( lm( Nicotine_content ~ IsLorillard + IsMethol + IsFiltered + IsMethol:IsFiltered, data=DF ) )

summary( lm( Nicotine_content ~ IsLorillard + IsMethol + IsFiltered + IsLorillard:IsMethol + IsLorillard:IsFiltered + IsMethol:IsFiltered, data=DF ) )

logm = lm( log(Nicotine_content) ~ IsLorillard + IsMethol + IsFiltered, data=DF )
summary(logm)

# Lets look for some outliers:
#
plot( m, which=1 )